Data Representation Structure to Support Clinical Decision-Making in the Pediatric Intensive Care Unit: Interview Study and Preliminary Decision Support Interface Design.

BACKGROUND: Clinical decision-making is a complex cognitive process that relies on the interpretation of a large variety of data from different sources and involves the use of knowledge bases and scientific recommendations. The representation of clinical data plays a key role in the speed and efficiency of its interpretation. In addition, the increasing use of clinical decision support systems (CDSSs) provides assistance to clinicians in their practice, allowing them to improve patient outcomes. In the pediatric intensive care unit (PICU), clinicians must process high volumes of data and deal with ever-growing workloads. As they use multiple systems daily to assess patients' status and to adjust the health care plan, including electronic health records (EHR), clinical systems (eg, laboratory, imaging and pharmacy), and connected devices (eg, bedside monitors, mechanical ventilators, intravenous pumps, and syringes), clinicians rely mostly on their judgment and ability to trace relevant data for decision-making. In these circumstances, the lack of optimal data structure and adapted visual representation hinder clinician's cognitive processes and clinical decision-making skills. OBJECTIVE: In this study, we designed a prototype to optimize the representation of clinical data collected from existing sources (eg, EHR, clinical systems, and devices) via a structure that supports the integration of a home-developed CDSS in the PICU. This study was based on analyzing end user needs and their clinical workflow. METHODS: First, we observed clinical activities in a PICU to secure a better understanding of the workflow in terms of staff tasks and their use of EHR on a typical work shift. Second, we conducted interviews with 11 clinicians from different staff categories (eg, intensivists, fellows, nurses, and nurse practitioners) to compile their needs for decision support. Third, we structured the data to design a prototype that illustrates the proposed representation. We used a brain injury care scenario to validate the relevance of integrated data and the utility of main functionalities in a clinical context. Fourth, we held design meetings with 5 clinicians to present, revise, and adapt the prototype to meet their needs. RESULTS: We created a structure with 3 levels of abstraction-unit level, patient level, and system level-to optimize clinical data representation and display for efficient patient assessment and to provide a flexible platform to host the internally developed CDSS. Subsequently, we designed a preliminary prototype based on this structure. CONCLUSIONS: The data representation structure allows prioritizing patients via criticality indicators, assessing their conditions using a personalized dashboard, and monitoring their courses based on the evolution of clinical values. Further research is required to define and model the concepts of criticality, problem recognition, and evolution. Furthermore, feasibility tests will be conducted to ensure user satisfaction.

Adaptation of Autoencoder for Sparsity Reduction From Clinical Notes Representation Learning.

When dealing with clinical text classification on a small dataset, recent studies have confirmed that a well-tuned multilayer perceptron outperforms other generative classifiers, including deep learning ones. To increase the performance of the neural network classifier, feature selection for the learning representation can effectively be used. However, most feature selection methods only estimate the degree of linear dependency between variables and select the best features based on univariate statistical tests. Furthermore, the sparsity of the feature space involved in the learning representation is ignored. GOAL: Our aim is, therefore, to access an alternative approach to tackle the sparsity by compressing the clinical representation feature space, where limited French clinical notes can also be dealt with effectively. METHODS: This study proposed an autoencoder learning algorithm to take advantage of sparsity reduction in clinical note representation. The motivation was to determine how to compress sparse, high-dimensional data by reducing the dimension of the clinical note representation feature space. The classification performance of the classifiers was then evaluated in the trained and compressed feature space. RESULTS: The proposed approach provided overall performance gains of up to 3% for each test set evaluation. Finally, the classifier achieved 92% accuracy, 91% recall, 91% precision, and 91% f1-score in detecting the patient's condition. Furthermore, the compression working mechanism and the autoencoder prediction process were demonstrated by applying the theoretic information bottleneck framework. Clinical and Translational Impact Statement- An autoencoder learning algorithm effectively tackles the problem of sparsity in the representation feature space from a small clinical narrative dataset. Significantly, it can learn the best representation of the training data because of its lossless compression capacity compared to other approaches. Consequently, its downstream classification ability can be significantly improved, which cannot be done using deep learning models.

Multimodality Video Acquisition System for the Assessment of Vital Distress in Children.

In children, vital distress events, particularly respiratory, go unrecognized. To develop a standard model for automated assessment of vital distress in children, we aimed to construct a prospective high-quality video database for critically ill children in a pediatric intensive care unit (PICU) setting. The videos were acquired automatically through a secure web application with an application programming interface (API). The purpose of this article is to describe the data acquisition process from each PICU room to the research electronic database. Using an Azure Kinect DK and a Flir Lepton 3.5 LWIR attached to a Jetson Xavier NX board and the network architecture of our PICU, we have implemented an ongoing high-fidelity prospectively collected video database for research, monitoring, and diagnostic purposes. This infrastructure offers the opportunity to develop algorithms (including computational models) to quantify vital distress in order to evaluate vital distress events. More than 290 RGB, thermographic, and point cloud videos of each 30 s have been recorded in the database. Each recording is linked to the patient's numerical phenotype, i.e., the electronic medical health record and high-resolution medical database of our research center. The ultimate goal is to develop and validate algorithms to detect vital distress in real time, both for inpatient care and outpatient management.

Hemodynamic assessment in children after cardiac surgery: A pilot study on the value of infrared thermography.

Introduction: Low cardiac output syndrome in the postoperative period after cardiac surgery leads to an increase in tissue oxygen extraction, assessed by the oxygen extraction ratio. Measurement of the oxygen extraction ratio requires blood gases to be taken. However, the temperature of the skin and various parts of the body is a direct result of blood flow distribution and can be monitored using infrared thermography. Thus, we conducted a prospective clinical study to evaluate the correlation between the thermal gradient obtained by infrared thermography and the oxygen extraction ratio in children at risk for low cardiac output after cardiac surgery. Methods: Children aged 0 to 18 years, having undergone cardiac surgery with cardio-pulmonary bypass in a pediatric intensive care unit were included in the study. One to 4 thermal photos were taken per patient using the FLIR One Pro thermal imaging camera. The thermal gradient between the central temperature of the inner canthus of the eye and the peripheral temperature was compared to the concomitant oxygen extraction ratio calculated from blood gases. Results: 41 patients were included with a median age of 6 months (IQR 3-48) with median Risk Adjustment for Congenital Heart Surgery-1 score was 2 (IQR 2-3). Eighty nine thermal photos were analyzed. The median thermal gradient was 2.5 °C (IQR 1,01-4.04). The median oxygen extraction ratio was 35% (IQR 26-42). Nine patients had an oxygen extraction ratio ≥ 50%. A significant but weak correlation was found between the thermal gradient and the oxygen extraction ratio (Spearman's test p = 0.25, p = 0.016). Thermal gradient was not correlated with any other clinical or biologic markers of low cardiac output. Only young age was an independent factor associated with an increase in the thermal gradient. Conclusion: In this pilot study, which included mainly children without severe cardiac output decrease, a significant but weak correlation between thermal gradient by infrared thermography and oxygen extraction ratio after pediatric cardiac surgery was observed. Infrared thermography is a promising non-invasive technology that could be included in multimodal monitoring of postoperative cardiac surgery patients. However, a clinical trial including more severe children is needed.

Optical Thermography Infrastructure to Assess Thermal Distribution in Critically Ill Children.

The temperature distribution at the skin surface could be a useful tool to monitor changes in cardiac output. Goal: The aim of this study was to explore infrared thermography as a method to analyze temperature profiles of critically ill children. Methods: Patients admitted to the pediatric intensive care unit (PICU) were included in this study. An infrared sensor was used to take images in clinical conditions. The infrared core and limb temperatures (θc & θl) were extracted, as well as temperatures along a line drawn between these two regions. Results: The median [interquartile range] θc extracted from the images was 33.88°C [32.74-34.19] and the median θl was 30.21°C [28.89-33.13]. There was a good correlation between the θc and the clinical axillary temperature (rho = 0.39, p-value = 0.016). There was also a good correlation between the θc and θl (rho = 0.66, p-value = 1.2 e-05). Conclusion: Thermography was found to be effective to estimate the body temperature. Correlation with specific clinical conditions needs further study.

Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation.

The rapid progress in clinical data management systems and artificial intelligence approaches enable the era of personalized medicine. Intensive care units (ICUs) are ideal clinical research environments for such development because they collect many clinical data and are highly computerized. Goal: We designed a retrospective clinical study on a prospective ICU database using clinical natural language to help in the early diagnosis of heart failure in critically ill children. Methods: The methodology consisted of empirical experiments of a learning algorithm to learn the hidden interpretation and presentation of the French clinical note data. This study included 1386 patients' clinical notes with 5444 single lines of notes. There were 1941 positive cases (36% of total) and 3503 negative cases classified by two independent physicians using a standardized approach. Results: The multilayer perceptron neural network outperforms other discriminative and generative classifiers. Consequently, the proposed framework yields an overall classification performance with 89% accuracy, 88% recall, and 89% precision. Conclusions: This study successfully applied learning representation and machine learning algorithms to detect heart failure in a single French institution from clinical natural language. Further work is needed to use the same methodology in other languages and institutions.

Arterial Partial Pressures of Carbon Dioxide Estimation Using Non-Invasive Parameters in Mechanically Ventilated Children.

OBJECTIVE: We aim to create a predictive model capable of giving a noninvasive, immediate and reliable estimate of the arterial partial pressure of carbon dioxide (PaCO2) in mechanically ventilated children with a better reliability than its estimation from end-tidal CO2 (PetCO2) and minute ventilation volume (Vmin) evolution. METHODS: We collected data from the Intensive Care Unit (ICU) database of Sainte-Justine University Hospital (Montreal, Canada) and used the multilayer perceptron (MLP) to estimate the PaCO2. Input data were (1) Arterial blood gas (ABG) at a previous time to calibrate the model, (2) mechanical ventilator parameters and (3) pulse oximetry. The data were divided into four groups depending on the time gap between previous ABG and its prediction: [0 h, 2 h], [2 h, 6 h], [6 h, 12 h] and [12 h, 24 h]. RESULTS: We included 17,329 ABGs collected from 527 patients between May 2015 and October 2018. Median age was 6.7 months (interquartile range 1-60) and female proportion was 45%. Patients had a median of 13 ABGs per patient (IQR 5-34). The accuracy of the models in the four groups was 18%, 18%, 19% and 25% higher than the minute volume models and the PetCO2 models (4% to 11%, respectively). CONCLUSION: Our model based on noninvasive parameters was able to better estimate the PaCO2 in mechanically ventilated children when compared to the traditional techniques. SIGNIFICANCE: ABG analysis is very important in ICU; it is the gold standard in respiratory and acid-base evaluation. ABG is invasive, painful and risky. Our approach, noninvasive and reliable, is an alternative for optimizing mechanical ventilator settings, thus providing better care for patients.

Automatic eye localization for hospitalized infants and children using convolutional neural networks.

BACKGROUND: Reliable localization and tracking of the eye region in the pediatric hospital environment is a significant challenge for clinical decision support and patient monitoring applications. Existing work in eye localization achieves high performance on adult datasets but performs poorly in the busy pediatric hospital environment, where face appearance varies because of age, position and the presence of medical equipment. METHODS: We developed two new datasets: a training dataset using public image data from internet searches, and a test dataset using 59 recordings of patients in a pediatric intensive care unit. We trained two eye localization models, using the Faster R-CNN algorithm to fine-tune a pre-trained ResNet base network, and evaluated them using the images from the pediatric ICU. RESULTS: The convolutional neural network trained with a combination of adult and child data achieved an 79.7% eye localization rate, significantly higher than the model trained on adult data alone. With additional pre-processing to equalize image contrast, the localization rate rises to 84%. CONCLUSION: The results demonstrate the potential of convolutional neural networks for eye localization and tracking in a pediatric ICU setting, even when training data is limited. We obtained significant performance gains by adding task-specific images to the training dataset, highlighting the need for custom models and datasets for specialized applications like pediatric patient monitoring. The moderate size of our added training dataset shows that it is feasible to develop an internal training dataset for clinical computer vision applications, and apply it with transfer learning to fine-tune existing pre-trained models.

Advancements in Methods and Camera-Based Sensors for the Quantification of Respiration.

Assessment of respiratory function allows early detection of potential disorders in the respiratory system and provides useful information for medical management. There is a wide range of applications for breathing assessment, from measurement systems in a clinical environment to applications involving athletes. Many studies on pulmonary function testing systems and breath monitoring have been conducted over the past few decades, and their results have the potential to broadly impact clinical practice. However, most of these works require physical contact with the patient to produce accurate and reliable measures of the respiratory function. There is still a significant shortcoming of non-contact measuring systems in their ability to fit into the clinical environment. The purpose of this paper is to provide a review of the current advances and systems in respiratory function assessment, particularly camera-based systems. A classification of the applicable research works is presented according to their techniques and recorded/quantified respiration parameters. In addition, the current solutions are discussed with regards to their direct applicability in different settings, such as clinical or home settings, highlighting their specific strengths and limitations in the different environments.

A Hierarchical Learning Approach for Human Action Recognition.

In the domain of human action recognition, existing works mainly focus on using RGB, depth, skeleton and infrared data for analysis. While these methods have the benefit of being non-invasive, they can only be used within limited setups, are prone to issues such as occlusion and often need substantial computational resources. In this work, we address human action recognition through inertial sensor signals, which have a vast quantity of practical applications in fields such as sports analysis and human-machine interfaces. For that purpose, we propose a new learning framework built around a 1D-CNN architecture, which we validated by achieving very competitive results on the publicly available UTD-MHAD dataset. Moreover, the proposed method provides some answers to two of the greatest challenges currently faced by action recognition algorithms, which are (1) the recognition of high-level activities and (2) the reduction of their computational cost in order to make them accessible to embedded devices. Finally, this paper also investigates the tractability of the features throughout the proposed framework, both in time and duration, as we believe it could play an important role in future works in order to make the solution more intelligible, hardware-friendly and accurate.

Using machine learning models to predict oxygen saturation following ventilator support adjustment in critically ill children: A single center pilot study.

BACKGROUND: In an intensive care units, experts in mechanical ventilation are not continuously at patient's bedside to adjust ventilation settings and to analyze the impact of these adjustments on gas exchange. The development of clinical decision support systems analyzing patients' data in real time offers an opportunity to fill this gap. OBJECTIVE: The objective of this study was to determine whether a machine learning predictive model could be trained on a set of clinical data and used to predict transcutaneous hemoglobin oxygen saturation 5 min (5min SpO2) after a ventilator setting change. DATA SOURCES: Data of mechanically ventilated children admitted between May 2015 and April 2017 were included and extracted from a high-resolution research database. More than 776,727 data rows were obtained from 610 patients, discretized into 3 class labels (< 84%, 85% to 91% and c92% to 100%). PERFORMANCE METRICS OF PREDICTIVE MODELS: Due to data imbalance, four different data balancing processes were applied. Then, two machine learning models (artificial neural network and Bootstrap aggregation of complex decision trees) were trained and tested on these four different balanced datasets. The best model predicted SpO2 with area under the curves < 0.75. CONCLUSION: This single center pilot study using machine learning predictive model resulted in an algorithm with poor accuracy. The comparison of machine learning models showed that bagged complex trees was a promising approach. However, there is a need to improve these models before incorporating them into a clinical decision support systems. One potentially solution for improving predictive model, would be to increase the amount of data available to limit over-fitting that is potentially one of the cause for poor classification performances for 2 of the three class labels.

Active Learning of the HL7 Medical Standard.

Health Level Seven (HL7®) is a standard for exchanging information between medical information systems. It is widely deployed and covers the exchange of information in several functional domains. It is very important and crucial to achieve interoperability in healthcare. HL7 competences are needed by all professionals touching information technology in healthcare. However, learning the standard has always been long and difficult due to its large breadth as well as to large and complex documentation. In this paper, we describe an innovative active learning approach based on solving problems from real clinical scenarios to learn the HL7 standard, quickly. We present the clinical scenarios used to achieve learning. For each scenario, we describe and discuss the learning objectives, clinical problem, clinical data, scaffolding introduction to the standard, software used, and the work required from the students. We present and discuss the results obtained by implementing the proposed approach during several semesters as part of a graduate course. Our proposed method has proven that HL7 can be learned quickly. We were successful in enabling students of different backgrounds to gain confidence and get familiar with a complex healthcare standard without the need for any software development skill.

3D imaging system for respiratory monitoring in pediatric intensive care environment.

Assessment of respiratory activity in pediatric intensive care unit allows a comprehensive view of the patient's condition. This allows the identification of high-risk cases for prompt and appropriate medical treatment. Numerous research works on respiration monitoring have been conducted in recent years. However, most of them are unsuitable for clinical environment or require physical contact with the patient, which limits their efficiency. In this paper, we present a novel system for measuring the breathing pattern based on a computer vision method and contactless design. Our 3D imaging system is specifically designed for pediatric intensive care environment, which distinguishes it from the other imaging methods. Indeed, previous works are mostly limited to the use of conventional video acquisition devices, in addition to not considering the constraints imposed by intensive care environment. The proposed system uses depth information captured by two (Red Green Blue-Depth) RGB-D cameras at different view angles, by considering the intensive care unit constraints. Depth information is then exploited to reconstruct a 3D surface of a patient's torso with high temporal and spatial resolution and large spatial coverage. Our system captures the motion information for the top of the torso surface as well as for its both lateral sides. For each reconstruction, the volume is estimated through a recursive subdivision of the 3D space into cubic unit elements. The volume change is then calculated through a subtraction technique between successive reconstructions. We tested our system in the pediatric intensive care unit of the Sainte-Justine university hospital center, where it was compared to the gold standard method currently used in pediatric intensive care units. The performed experiments showed a very high accuracy and precision of the proposed imaging system in estimating respiratory rate and tidal volume.

Computed Tomography Image Compressibility and Limitations of Compression Ratio-Based Guidelines.

Finding optimal compression levels for diagnostic imaging is not an easy task. Significant compressibility variations exist between modalities, but little is known about compressibility variations within modalities. Moreover, compressibility is affected by acquisition parameters. In this study, we evaluate the compressibility of thousands of computed tomography (CT) slices acquired with different slice thicknesses, exposures, reconstruction filters, slice collimations, and pitches. We demonstrate that exposure, slice thickness, and reconstruction filters have a significant impact on image compressibility due to an increased high frequency content and a lower acquisition signal-to-noise ratio. We also show that compression ratio is not a good fidelity measure. Therefore, guidelines based on compression ratio should ideally be replaced with other compression measures better correlated with image fidelity. Value-of-interest (VOI) transformations also affect the perception of quality. We have studied the effect of value-of-interest transformation and found significant masking of artifacts when window is widened.

Compressibility variations of JPEG2000 compressed computed tomography.

Compression is increasingly used in medical applications to enable efficient and universally accessible electronic health records. However, lossy compression introduces artifacts that can alter diagnostic accuracy, interfere with image processing algorithms and cause liability issues in cases of diagnostic errors. Compression guidelines were introduced to mitigate these issues and foster the use of modern compression algorithms with diagnostic imaging. However, these guidelines are usually defined as maximum compression ratios for each imaging protocol and do not take compressibility variations due to image content into account. In this paper we have evaluated the compressibility of thousands of computed tomography slices of an anthropomorphic thoracic phantom acquired with different parameters. We have shown that exposure, slice thickness and reconstruction filters have a significant impact on compressibility suggesting that guidelines based solely on compression ratios may be inadequate.

Testing of Electronic Healthcare Record images and reports viewer.

Electronic Health Record (EHR) is a distributed system that results from the cooperation of several heterogeneous and autonomous subsystems. It improves health care by enabling access to prior diagnostic information to assist in health decisions. We focus on the image and imaging report visualization component that needs to interoperate with several other systems to enable healthcare professionals visualize a patient's imaging record. We propose and describe an environment that has been built and used to facilitate the development of the viewer component. This environment has also been used to test and verify the interoperability of the viewer component with other EHR components in accordance with the Integrating the Healthcare Enterprise (IHE) technical framework. It has also been used to demonstrate functionalities, to educate end users, and to train maintenance and test engineers. Moreover, it has been used for acceptance testing as part of an EHR deployment project. We also discuss the challenges we faced in constructing the testing data and describe the software developed to automatically populate the test environment with valid data.

Deployment of a fully-automated green fluorescent protein imaging system in a high arctic autonomous greenhouse.

Higher plants are an integral part of strategies for sustained human presence in space. Space-based greenhouses have the potential to provide closed-loop recycling of oxygen, water and food. Plant monitoring systems with the capacity to remotely observe the condition of crops in real-time within these systems would permit operators to take immediate action to ensure optimum system yield and reliability. One such plant health monitoring technique involves the use of reporter genes driving fluorescent proteins as biological sensors of plant stress. In 2006 an initial prototype green fluorescent protein imager system was deployed at the Arthur Clarke Mars Greenhouse located in the Canadian High Arctic. This prototype demonstrated the advantageous of this biosensor technology and underscored the challenges in collecting and managing telemetric data from exigent environments. We present here the design and deployment of a second prototype imaging system deployed within and connected to the infrastructure of the Arthur Clarke Mars Greenhouse. This is the first imager to run autonomously for one year in the un-crewed greenhouse with command and control conducted through the greenhouse satellite control system. Images were saved locally in high resolution and sent telemetrically in low resolution. Imager hardware is described, including the custom designed LED growth light and fluorescent excitation light boards, filters, data acquisition and control system, and basic sensing and environmental control. Several critical lessons learned related to the hardware of small plant growth payloads are also elaborated.

Teaching DICOM by problem solving.

The Digital Imaging and Communications in Medicine (DICOM) is the standard for encoding and communicating medical imaging information. It is used in radiology as well as in many other imaging domains such as ophthalmology, dentistry, and pathology. DICOM information objects are used to encode medical images or information about the images. Their usage outside of the imaging department is increasing, especially with the sharing of medical images within Electronic Health Record systems. However, learning DICOM is long and difficult because it defines and uses many specific abstract concepts that relate to each other. In this paper, we present an approach, based on problem solving, for teaching DICOM as part of a graduate course on healthcare information. The proposed approach allows students with diversified background and no software development experience to grasp a large breadth of knowledge in a very short time.

Using JPEG 2000 interactive protocol to stream a large image or a large image set.

The electronic health record (EHR) is expected to improve the quality of care by enabling access to relevant information at the diagnostic decision moment. During deployment efforts for including images in the EHR, a main challenge has come up from the need to compare old images with current ones. When old images reside in a different system, they need to be imported for visualization which leads to a problem related to persistency management and information consistency. A solution consisting in avoiding image import is achievable with image streaming. In this paper we present, evaluate, and discuss two medical-specific streaming use cases: displaying a large image such as a digital mammography image and displaying a large set of relatively small images such as a large CT series.

IHE cross-enterprise document sharing for imaging: interoperability testing software.

BACKGROUND: With the deployments of Electronic Health Records (EHR), interoperability testing in healthcare is becoming crucial. EHR enables access to prior diagnostic information in order to assist in health decisions. It is a virtual system that results from the cooperation of several heterogeneous distributed systems. Interoperability between peers is therefore essential. Achieving interoperability requires various types of testing. Implementations need to be tested using software that simulates communication partners, and that provides test data and test plans. RESULTS: In this paper we describe a software that is used to test systems that are involved in sharing medical images within the EHR. Our software is used as part of the Integrating the Healthcare Enterprise (IHE) testing process to test the Cross Enterprise Document Sharing for imaging (XDS-I) integration profile. We describe its architecture and functionalities; we also expose the challenges encountered and discuss the elected design solutions. CONCLUSIONS: EHR is being deployed in several countries. The EHR infrastructure will be continuously evolving to embrace advances in the information technology domain. Our software is built on a web framework to allow for an easy evolution with web technology. The testing software is publicly available; it can be used by system implementers to test their implementations. It can also be used by site integrators to verify and test the interoperability of systems, or by developers to understand specifications ambiguities, or to resolve implementations difficulties.